© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 123
    Prev
    Next
    INDEX
    Explanations

    medical terms and conditions related to the brain

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    308
    +0.14
    0.7%
    471
    +0.12
    0.5%
    59
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.08
    588
    +0.12
    0.05
    471
    +0.11
    0.04
    Negative Logits
    IELD
    -0.82
    creen
    -0.81
    ndra
    -0.81
    HCR
    -0.79
    hirt
    -0.78
    wagen
    -0.77
    fman
    -0.75
    eka
    -0.75
    cake
    -0.74
    hift
    -0.74
    POSITIVE LOGITS
    uders
    1.05
    uding
    0.87
    ordinary
    0.85
    inx
    0.85
    imate
    0.81
    usions
    0.81
     intr
    0.80
    igent
    0.80
    acy
    0.79
     pneum
    0.77
    Activations Density 0.761%

    No Known Activations